节点文献

一种基于大数据的出生人口预测优化算法

An Optimization Algorithm of Birth Prediction Based on Big Data

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 王征征张卫钢孙道斌张鑫王培丞

【Author】 WANG Zhengzheng;ZHANG Weigang;SUN Daobin;ZHANG Xin;WANG Peicheng;School of Information Engineering,Chang’an University;Xi’an Are Web Technology Development Co.,Ltd.;

【机构】 长安大学信息工程学院西安网是科技发展有限公司

【摘要】 研究出生人口预测问题,对于未来人口的预测起着极其重要的作用。如今常用的出生人口预测算法都是基于影响出生人口的主观因素而设计的,如各年龄段妇女总数、死亡率、生育率等,没有考虑经济因素、国家政策因素、国民受教育程度、人口总抚养比等客观因素的影响。近年来我国实际的出生量远低于国家所预测的出生量就充分体现了相关算法所存在的缺陷。鉴于此,论文在考虑了客观因素的条件下,利用历年来我国的人口相关数据并结合主成分分析法、多元线性回归算法、Spass软件等算法和软件对分年龄组生育率法进行了优化,从而得到了一种新的出生人口优化算法。仿真数据结果表明,该优化预测算法极大地提高了出生人口预测的精度,具有一定的理论参考意义和较高实用价值。

【Abstract】 Studying the prediction problem of birth population plays an extremely important role in the prediction of future population. Nowadays,the common prediction algorithms of birth population are based on the subjective factors that affect the birth population,such as the total number of women,the mortality,the fertility rate and so on,and the influence of the objective factors such as the economic factors,the national policy factors,the education level of the national population,the total rearing ratio of the population and so on. In recent years,China’s actual birth rate is far lower than the country’s predicted birth rate,which fully reflects the defects of the relevant algorithm. In view of this,with the consideration of the objective factors,this paper optimizes the age group fertility rate method by combining the population related data of our country over the years,combined with the principal component analysis,multiple linear regression algorithm,Spass software and other algorithms and software,thus a new birth population optimization algorithm is obtained. The simulation results show that the optimal prediction algorithm greatly improves the accuracy of the prediction of birth population,and has a certain theoretical reference significance and a higher practical value.

  • 【文献出处】 计算机与数字工程 ,Computer & Digital Engineering , 编辑部邮箱 ,2020年03期
  • 【分类号】C924.2;TP311.13
  • 【被引频次】2
  • 【下载频次】385
节点文献中: 

本文链接的文献网络图示:

本文的引文网络